© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27078
    Prev
    Next
    INDEX
    Explanations

    distinct values or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thic
    -0.10
    zinho
    -0.09
    teri
    -0.08
    enov
    -0.08
    hlen
    -0.08
    refour
    -0.08
    editary
    -0.07
    wards
    -0.07
    rlen
    -0.07
    大亨
    -0.07
    POSITIVE LOGITS
    ively
    0.18
    iveness
    0.12
    ness
    0.12
    s
    0.10
    eting
    0.09
    ely
    0.09
    verständlich
    0.08
    inct
    0.08
    uous
    0.08
    à§įর
    0.08
    Activations Density 0.010%

    No Known Activations